Structured Embedding Models for Grouped Data
arXiv:1709.10367
Abstract
Word embeddings are a powerful approach for analyzing language, and exponential family embeddings (EFE) extend them to other types of data. Here we develop structured exponential family embeddings (S-EFE), a method for discovering embeddings that vary across related groups of data. We study how the word usage of U.S. Congressional speeches varies across states and party affiliation, how words are used differently across sections of the ArXiv, and how the co-purchase patterns of groceries can vary across seasons. Key to the success of our method is that the groups share statistical information. We develop two sharing strategies: hierarchical modeling and amortization. We demonstrate the benefits of this approach in empirical studies of speeches, abstracts, and shopping baskets. We show how S-EFE enables group-specific interpretation of word usage, and outperforms EFE in predicting held-out data.
References in corpus (9)
- Auto-Encoding Variational Bayes
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Exploiting Similarities among Languages for Machine Translation
- Massively Multilingual Word Embeddings
- Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change
- Dynamic Word Embeddings
- Exponential Family Embeddings
- Temporal Analysis of Language through Neural Language Models
- Dynamic Bernoulli Embeddings for Language Evolution